Transmit Coefficients and Receive Combining Vector Design for OTA-FL with Imperfect CSI
For wireless federated learning systems, this work provides a practical solution to mitigate the impact of imperfect CSI on model aggregation, improving learning performance in realistic communication scenarios.
This paper addresses the problem of imperfect aggregation in over-the-air federated learning (OTA-FL) caused by channel state information (CSI) uncertainty. By jointly designing transmit coefficients and receive combining vectors, the proposed optimization framework minimizes long-term mean squared error (MSE) and reduces test accuracy degradation, achieving superior performance on Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets.
Over-the-air (OTA) computation has recently gained significant attentions as an effective approach to enhance the communication efficiency of wireless federated learning (FL). By enabling simultaneous transmission and aggregation of local model updates, OTA-FL can substantially reduce both latency and bandwidth consumption. However, a key challenge lies in the imperfect aggregation of global models caused by channel state information (CSI) uncertainty, which introduces distortion to the final learning performance. To address this issue, we study the long-term mean squared error (MSE) minimization problem for OTA-FL under imperfect CSI conditions. Through convergence analysis, we establish an upper bound for the time-averaged MSE, thereby revealing the effect of aggregation errors accumulated throughout multiple communication rounds on the overall training performances. Based on this analysis, an optimization framework is developed to minimize the long-term MSE via the joint design of (i) transmit coefficients at the local devices and (ii) receive combining vectors at the parameter server (PS). Since this alternating optimization approach requires non-causal CSI, a Lyapunov-based optimization method is further introduced to handle causal CSI scenarios. By incorporating virtual queues to characterize long-term energy consumption, the proposed method effectively decouples temporal dependencies and allows transmit coefficients to be optimized based on the causal CSI of each aggregation round. Comprehensive evaluations on Fashion-MNIST, CIFAR-10 and CIFAR-100 datasets have demonstrated that the proposed algorithms can significantly reduce the degradation of test accuracy caused by imperfect CSI. Comparisons with other benchmark schemes further verify the superiority of our proposed algorithms.